Update model

README.md

@@ -0,0 +1,517 @@
+---
+tags:
+- espnet
+- audio
+- text-to-speech
+language: en
+datasets:
+- emilia_full
+license: cc-by-4.0
+---
+
+## ESPnet2 TTS model
+
+### `NewGame/Emilia-vits-espnet2`
+
+This model was trained by NewGamezzz using emilia_full recipe in [espnet](https://github.com/espnet/espnet/).
+
+### Demo: How to use in ESPnet2
+
+Follow the [ESPnet installation instructions](https://espnet.github.io/espnet/installation.html)
+if you haven't done that already.
+
+```bash
+cd espnet
+git checkout 7d46ef980eb56d14c23201d26ff4eceec97d0b3a
+pip install -e .
+cd egs2/emilia_full/tts1
+./run.sh --skip_data_prep false --skip_train true --download_model NewGame/Emilia-vits-espnet2
+```
+
+
+
+## TTS config
+
+<details><summary>expand</summary>
+
+```
+config: conf/tuning/train_xvector_vits_large_grad_clip_original_batch_size.yaml
+print_config: false
+log_level: INFO
+drop_last_iter: false
+dry_run: false
+iterator_type: sequence
+valid_iterator_type: null
+output_dir: exp/tts_train_xvector_vits_large_grad_clip_original_batch_size_raw_phn_tacotron_g2p_en
+ngpu: 1
+seed: 777
+num_workers: 0
+num_att_plot: 3
+dist_backend: nccl
+dist_init_method: env://
+dist_world_size: 4
+dist_rank: 0
+local_rank: 0
+dist_master_addr: localhost
+dist_master_port: 53813
+dist_launcher: null
+multiprocessing_distributed: true
+unused_parameters: true
+sharded_ddp: false
+use_deepspeed: false
+deepspeed_config: null
+gradient_as_bucket_view: true
+ddp_comm_hook: null
+cudnn_enabled: true
+cudnn_benchmark: false
+cudnn_deterministic: false
+use_tf32: false
+collect_stats: false
+write_collected_feats: false
+max_epoch: 800
+patience: null
+val_scheduler_criterion:
+- valid
+- loss
+early_stopping_criterion:
+- valid
+- loss
+- min
+best_model_criterion:
+-   - train
+    - total_count
+    - max
+keep_nbest_models: 10
+nbest_averaging_interval: 0
+grad_clip: 1.0
+grad_clip_type: 2.0
+grad_noise: false
+accum_grad: 1
+no_forward_run: false
+resume: true
+train_dtype: float32
+use_amp: false
+log_interval: 50
+use_matplotlib: true
+use_tensorboard: true
+create_graph_in_tensorboard: false
+use_wandb: false
+wandb_project: null
+wandb_id: null
+wandb_entity: null
+wandb_name: null
+wandb_model_log_interval: -1
+detect_anomaly: false
+use_adapter: false
+adapter: lora
+save_strategy: all
+adapter_conf: {}
+pretrain_path: null
+init_param: []
+ignore_init_mismatch: false
+freeze_param: []
+num_iters_per_epoch: 1000
+batch_size: 20
+valid_batch_size: null
+batch_bins: 8000000
+valid_batch_bins: null
+category_sample_size: 10
+upsampling_factor: 0.5
+category_upsampling_factor: 0.5
+dataset_upsampling_factor: 0.5
+dataset_scaling_factor: 1.2
+max_batch_size: null
+min_batch_size: 1
+train_shape_file:
+- exp/tts_stats_raw_linear_spectrogram_phn_tacotron_g2p_en/train/text_shape.phn
+- exp/tts_stats_raw_linear_spectrogram_phn_tacotron_g2p_en/train/speech_shape
+valid_shape_file:
+- exp/tts_stats_raw_linear_spectrogram_phn_tacotron_g2p_en/valid/text_shape.phn
+- exp/tts_stats_raw_linear_spectrogram_phn_tacotron_g2p_en/valid/speech_shape
+batch_type: numel
+valid_batch_type: null
+fold_length:
+- 150
+- 204800
+sort_in_batch: descending
+shuffle_within_batch: false
+sort_batch: descending
+multiple_iterator: false
+chunk_length: 500
+chunk_shift_ratio: 0.5
+num_cache_chunks: 1024
+chunk_excluded_key_prefixes: []
+chunk_default_fs: null
+chunk_max_abs_length: null
+chunk_discard_short_samples: true
+train_data_path_and_name_and_type:
+-   - dump/raw/tr_no_dev/text
+    - text
+    - text
+-   - dump/raw/tr_no_dev/wav.scp
+    - speech
+    - sound
+-   - dump/xvector/tr_no_dev/xvector.scp
+    - spembs
+    - kaldi_ark
+valid_data_path_and_name_and_type:
+-   - dump/raw/dev/text
+    - text
+    - text
+-   - dump/raw/dev/wav.scp
+    - speech
+    - sound
+-   - dump/xvector/dev/xvector.scp
+    - spembs
+    - kaldi_ark
+multi_task_dataset: false
+allow_variable_data_keys: false
+max_cache_size: 0.0
+max_cache_fd: 32
+allow_multi_rates: false
+valid_max_cache_size: null
+exclude_weight_decay: false
+exclude_weight_decay_conf: {}
+optim: adamw
+optim_conf:
+    lr: 0.0002
+    betas:
+    - 0.8
+    - 0.99
+    eps: 1.0e-09
+    weight_decay: 0.0
+scheduler: exponentiallr
+scheduler_conf:
+    gamma: 0.999
+optim2: adamw
+optim2_conf:
+    lr: 0.0002
+    betas:
+    - 0.8
+    - 0.99
+    eps: 1.0e-09
+    weight_decay: 0.0
+scheduler2: exponentiallr
+scheduler2_conf:
+    gamma: 0.999
+generator_first: false
+skip_discriminator_prob: 0.0
+token_list:
+- <blank>
+- <unk>
+- ' '
+- T
+- AH0
+- N
+- S
+- R
+- D
+- L
+- K
+- IH1
+- DH
+- M
+- Z
+- EH1
+- AH1
+- AE1
+- IH0
+- ','
+- W
+- UW1
+- AY1
+- IY1
+- .
+- P
+- V
+- B
+- AA1
+- F
+- ER0
+- IY0
+- EY1
+- AO1
+- OW1
+- HH
+- Y
+- NG
+- G
+- SH
+- AW1
+- JH
+- TH
+- CH
+- ER1
+- UH1
+- '?'
+- OW0
+- EH2
+- IH2
+- EY2
+- AY2
+- OW2
+- AA2
+- AE2
+- UW0
+- EH0
+- OY1
+- AH2
+- AO2
+- AE0
+- ZH
+- AY0
+- UW2
+- AA0
+- IY2
+- AO0
+- '...'
+- AW2
+- '!'
+- EY0
+- UH2
+- ER2
+- ''''
+- AW0
+- UH0
+- OY2
+- OY0
+- '... ...'
+- . ...
+- . .
+- ..
+- . . .
+- . . . .
+- . . . . .
+- '... .'
+- <sos/eos>
+odim: null
+model_conf: {}
+use_preprocessor: true
+token_type: phn
+bpemodel: null
+non_linguistic_symbols: null
+cleaner: tacotron
+g2p: g2p_en
+feats_extract: linear_spectrogram
+feats_extract_conf:
+    n_fft: 1024
+    hop_length: 256
+    win_length: null
+normalize: null
+normalize_conf: {}
+tts: vits
+tts_conf:
+    generator_type: vits_generator
+    generator_params:
+        hidden_channels: 256
+        spks: -1
+        spk_embed_dim: 192
+        global_channels: 256
+        segment_size: 32
+        text_encoder_attention_heads: 4
+        text_encoder_ffn_expand: 4
+        text_encoder_blocks: 8
+        text_encoder_positionwise_layer_type: conv1d
+        text_encoder_positionwise_conv_kernel_size: 3
+        text_encoder_positional_encoding_layer_type: rel_pos
+        text_encoder_self_attention_layer_type: rel_selfattn
+        text_encoder_activation_type: swish
+        text_encoder_normalize_before: true
+        text_encoder_dropout_rate: 0.1
+        text_encoder_positional_dropout_rate: 0.0
+        text_encoder_attention_dropout_rate: 0.1
+        use_macaron_style_in_text_encoder: true
+        use_conformer_conv_in_text_encoder: false
+        text_encoder_conformer_kernel_size: -1
+        decoder_kernel_size: 7
+        decoder_channels: 768
+        decoder_upsample_scales:
+        - 8
+        - 8
+        - 2
+        - 2
+        decoder_upsample_kernel_sizes:
+        - 16
+        - 16
+        - 4
+        - 4
+        decoder_resblock_kernel_sizes:
+        - 3
+        - 7
+        - 11
+        decoder_resblock_dilations:
+        -   - 1
+            - 3
+            - 5
+        -   - 1
+            - 3
+            - 5
+        -   - 1
+            - 3
+            - 5
+        use_weight_norm_in_decoder: true
+        posterior_encoder_kernel_size: 5
+        posterior_encoder_layers: 16
+        posterior_encoder_stacks: 1
+        posterior_encoder_base_dilation: 1
+        posterior_encoder_dropout_rate: 0.0
+        use_weight_norm_in_posterior_encoder: true
+        flow_flows: 4
+        flow_kernel_size: 5
+        flow_base_dilation: 1
+        flow_layers: 4
+        flow_dropout_rate: 0.0
+        use_weight_norm_in_flow: true
+        use_only_mean_in_flow: true
+        stochastic_duration_predictor_kernel_size: 3
+        stochastic_duration_predictor_dropout_rate: 0.5
+        stochastic_duration_predictor_flows: 4
+        stochastic_duration_predictor_dds_conv_layers: 3
+        vocabs: 87
+        aux_channels: 513
+    discriminator_type: hifigan_multi_scale_multi_period_discriminator
+    discriminator_params:
+        scales: 1
+        scale_downsample_pooling: AvgPool1d
+        scale_downsample_pooling_params:
+            kernel_size: 4
+            stride: 2
+            padding: 2
+        scale_discriminator_params:
+            in_channels: 1
+            out_channels: 1
+            kernel_sizes:
+            - 15
+            - 41
+            - 5
+            - 3
+            channels: 128
+            max_downsample_channels: 1024
+            max_groups: 16
+            bias: true
+            downsample_scales:
+            - 2
+            - 2
+            - 4
+            - 4
+            - 1
+            nonlinear_activation: LeakyReLU
+            nonlinear_activation_params:
+                negative_slope: 0.1
+            use_weight_norm: true
+            use_spectral_norm: false
+        follow_official_norm: false
+        periods:
+        - 2
+        - 3
+        - 5
+        - 7
+        - 11
+        period_discriminator_params:
+            in_channels: 1
+            out_channels: 1
+            kernel_sizes:
+            - 5
+            - 3
+            channels: 32
+            downsample_scales:
+            - 3
+            - 3
+            - 3
+            - 3
+            - 1
+            max_downsample_channels: 1024
+            bias: true
+            nonlinear_activation: LeakyReLU
+            nonlinear_activation_params:
+                negative_slope: 0.1
+            use_weight_norm: true
+            use_spectral_norm: false
+    generator_adv_loss_params:
+        average_by_discriminators: false
+        loss_type: mse
+    discriminator_adv_loss_params:
+        average_by_discriminators: false
+        loss_type: mse
+    feat_match_loss_params:
+        average_by_discriminators: false
+        average_by_layers: false
+        include_final_outputs: true
+    mel_loss_params:
+        fs: 22050
+        n_fft: 1024
+        hop_length: 256
+        win_length: null
+        window: hann
+        n_mels: 80
+        fmin: 0
+        fmax: null
+        log_base: null
+    lambda_adv: 1.0
+    lambda_mel: 45.0
+    lambda_feat_match: 2.0
+    lambda_dur: 1.0
+    lambda_kl: 1.0
+    sampling_rate: 22050
+    cache_generator_outputs: true
+    plot_pred_mos: false
+    mos_pred_tool: utmos
+pitch_extract: null
+pitch_extract_conf: {}
+pitch_normalize: null
+pitch_normalize_conf: {}
+energy_extract: null
+energy_extract_conf: {}
+energy_normalize: null
+energy_normalize_conf: {}
+required:
+- output_dir
+- token_list
+version: '202509'
+distributed: true
+```
+
+</details>
+
+
+
+### Citing ESPnet
+
+```BibTex
+@inproceedings{watanabe2018espnet,
+  author={Shinji Watanabe and Takaaki Hori and Shigeki Karita and Tomoki Hayashi and Jiro Nishitoba and Yuya Unno and Nelson Yalta and Jahn Heymann and Matthew Wiesner and Nanxin Chen and Adithya Renduchintala and Tsubasa Ochiai},
+  title={{ESPnet}: End-to-End Speech Processing Toolkit},
+  year={2018},
+  booktitle={Proceedings of Interspeech},
+  pages={2207--2211},
+  doi={10.21437/Interspeech.2018-1456},
+  url={http://dx.doi.org/10.21437/Interspeech.2018-1456}
+}
+
+
+
+
+@inproceedings{hayashi2020espnet,
+  title={{Espnet-TTS}: Unified, reproducible, and integratable open source end-to-end text-to-speech toolkit},
+  author={Hayashi, Tomoki and Yamamoto, Ryuichi and Inoue, Katsuki and Yoshimura, Takenori and Watanabe, Shinji and Toda, Tomoki and Takeda, Kazuya and Zhang, Yu and Tan, Xu},
+  booktitle={Proceedings of IEEE International Conference on Acoustics, Speech and Signal Processing (ICASSP)},
+  pages={7654--7658},
+  year={2020},
+  organization={IEEE}
+}
+
+
+```
+
+or arXiv:
+
+```bibtex
+@misc{watanabe2018espnet,
+  title={ESPnet: End-to-End Speech Processing Toolkit},
+  author={Shinji Watanabe and Takaaki Hori and Shigeki Karita and Tomoki Hayashi and Jiro Nishitoba and Yuya Unno and Nelson Yalta and Jahn Heymann and Matthew Wiesner and Nanxin Chen and Adithya Renduchintala and Tsubasa Ochiai},
+  year={2018},
+  eprint={1804.00015},
+  archivePrefix={arXiv},
+  primaryClass={cs.CL}
+}
+```

dump/xvector/dev/spk_xvector.ark

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:affc35e2e715c8760c68d2b4d159714f58364bb52a676e7e92bf45b19daa0089
+size 3895500

dump/xvector/dev/spk_xvector.scp

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:64a4caf62b898a9f08f881d84630d71f020a8a435ebe28bf2cec0585c41b2d8f
+size 282800

dump/xvector/eval/spk_xvector.ark

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:426d19bea97a23337f12434e31be01cf66e712b9ea51aad93d03a54072b1f8a8
+size 84564

dump/xvector/eval/spk_xvector.scp

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:56cafc9d2e5554f5b360319c000935b41e0fe732cbbb0968d798318efc0456fa
+size 4843

dump/xvector/tr_no_dev/spk_xvector.ark

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:42e0e59bdf97f8330d035169652b84e2a5f5d61a57d54a9e4a8a905f514520e5
+size 896806905

dump/xvector/tr_no_dev/spk_xvector.scp

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:c92bb17872d46b14fbffcd0b85404bc423e83164f5ea474dd1e4add2108fbc5b
+size 74312128

exp/tts_train_xvector_vits_large_grad_clip_original_batch_size_raw_phn_tacotron_g2p_en/785epoch.pth

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:a692546fc6873385bd2c8213d55e5a92f979190817b25940799588354b041c86
+size 575103133

exp/tts_train_xvector_vits_large_grad_clip_original_batch_size_raw_phn_tacotron_g2p_en/config.yaml

@@ -0,0 +1,434 @@
+config: conf/tuning/train_xvector_vits_large_grad_clip_original_batch_size.yaml
+print_config: false
+log_level: INFO
+drop_last_iter: false
+dry_run: false
+iterator_type: sequence
+valid_iterator_type: null
+output_dir: exp/tts_train_xvector_vits_large_grad_clip_original_batch_size_raw_phn_tacotron_g2p_en
+ngpu: 1
+seed: 777
+num_workers: 0
+num_att_plot: 3
+dist_backend: nccl
+dist_init_method: env://
+dist_world_size: 4
+dist_rank: 0
+local_rank: 0
+dist_master_addr: localhost
+dist_master_port: 53813
+dist_launcher: null
+multiprocessing_distributed: true
+unused_parameters: true
+sharded_ddp: false
+use_deepspeed: false
+deepspeed_config: null
+gradient_as_bucket_view: true
+ddp_comm_hook: null
+cudnn_enabled: true
+cudnn_benchmark: false
+cudnn_deterministic: false
+use_tf32: false
+collect_stats: false
+write_collected_feats: false
+max_epoch: 800
+patience: null
+val_scheduler_criterion:
+- valid
+- loss
+early_stopping_criterion:
+- valid
+- loss
+- min
+best_model_criterion:
+-   - train
+    - total_count
+    - max
+keep_nbest_models: 10
+nbest_averaging_interval: 0
+grad_clip: 1.0
+grad_clip_type: 2.0
+grad_noise: false
+accum_grad: 1
+no_forward_run: false
+resume: true
+train_dtype: float32
+use_amp: false
+log_interval: 50
+use_matplotlib: true
+use_tensorboard: true
+create_graph_in_tensorboard: false
+use_wandb: false
+wandb_project: null
+wandb_id: null
+wandb_entity: null
+wandb_name: null
+wandb_model_log_interval: -1
+detect_anomaly: false
+use_adapter: false
+adapter: lora
+save_strategy: all
+adapter_conf: {}
+pretrain_path: null
+init_param: []
+ignore_init_mismatch: false
+freeze_param: []
+num_iters_per_epoch: 1000
+batch_size: 20
+valid_batch_size: null
+batch_bins: 8000000
+valid_batch_bins: null
+category_sample_size: 10
+upsampling_factor: 0.5
+category_upsampling_factor: 0.5
+dataset_upsampling_factor: 0.5
+dataset_scaling_factor: 1.2
+max_batch_size: null
+min_batch_size: 1
+train_shape_file:
+- exp/tts_stats_raw_linear_spectrogram_phn_tacotron_g2p_en/train/text_shape.phn
+- exp/tts_stats_raw_linear_spectrogram_phn_tacotron_g2p_en/train/speech_shape
+valid_shape_file:
+- exp/tts_stats_raw_linear_spectrogram_phn_tacotron_g2p_en/valid/text_shape.phn
+- exp/tts_stats_raw_linear_spectrogram_phn_tacotron_g2p_en/valid/speech_shape
+batch_type: numel
+valid_batch_type: null
+fold_length:
+- 150
+- 204800
+sort_in_batch: descending
+shuffle_within_batch: false
+sort_batch: descending
+multiple_iterator: false
+chunk_length: 500
+chunk_shift_ratio: 0.5
+num_cache_chunks: 1024
+chunk_excluded_key_prefixes: []
+chunk_default_fs: null
+chunk_max_abs_length: null
+chunk_discard_short_samples: true
+train_data_path_and_name_and_type:
+-   - dump/raw/tr_no_dev/text
+    - text
+    - text
+-   - dump/raw/tr_no_dev/wav.scp
+    - speech
+    - sound
+-   - dump/xvector/tr_no_dev/xvector.scp
+    - spembs
+    - kaldi_ark
+valid_data_path_and_name_and_type:
+-   - dump/raw/dev/text
+    - text
+    - text
+-   - dump/raw/dev/wav.scp
+    - speech
+    - sound
+-   - dump/xvector/dev/xvector.scp
+    - spembs
+    - kaldi_ark
+multi_task_dataset: false
+allow_variable_data_keys: false
+max_cache_size: 0.0
+max_cache_fd: 32
+allow_multi_rates: false
+valid_max_cache_size: null
+exclude_weight_decay: false
+exclude_weight_decay_conf: {}
+optim: adamw
+optim_conf:
+    lr: 0.0002
+    betas:
+    - 0.8
+    - 0.99
+    eps: 1.0e-09
+    weight_decay: 0.0
+scheduler: exponentiallr
+scheduler_conf:
+    gamma: 0.999
+optim2: adamw
+optim2_conf:
+    lr: 0.0002
+    betas:
+    - 0.8
+    - 0.99
+    eps: 1.0e-09
+    weight_decay: 0.0
+scheduler2: exponentiallr
+scheduler2_conf:
+    gamma: 0.999
+generator_first: false
+skip_discriminator_prob: 0.0
+token_list:
+- <blank>
+- <unk>
+- ' '
+- T
+- AH0
+- N
+- S
+- R
+- D
+- L
+- K
+- IH1
+- DH
+- M
+- Z
+- EH1
+- AH1
+- AE1
+- IH0
+- ','
+- W
+- UW1
+- AY1
+- IY1
+- .
+- P
+- V
+- B
+- AA1
+- F
+- ER0
+- IY0
+- EY1
+- AO1
+- OW1
+- HH
+- Y
+- NG
+- G
+- SH
+- AW1
+- JH
+- TH
+- CH
+- ER1
+- UH1
+- '?'
+- OW0
+- EH2
+- IH2
+- EY2
+- AY2
+- OW2
+- AA2
+- AE2
+- UW0
+- EH0
+- OY1
+- AH2
+- AO2
+- AE0
+- ZH
+- AY0
+- UW2
+- AA0
+- IY2
+- AO0
+- '...'
+- AW2
+- '!'
+- EY0
+- UH2
+- ER2
+- ''''
+- AW0
+- UH0
+- OY2
+- OY0
+- '... ...'
+- . ...
+- . .
+- ..
+- . . .
+- . . . .
+- . . . . .
+- '... .'
+- <sos/eos>
+odim: null
+model_conf: {}
+use_preprocessor: true
+token_type: phn
+bpemodel: null
+non_linguistic_symbols: null
+cleaner: tacotron
+g2p: g2p_en
+feats_extract: linear_spectrogram
+feats_extract_conf:
+    n_fft: 1024
+    hop_length: 256
+    win_length: null
+normalize: null
+normalize_conf: {}
+tts: vits
+tts_conf:
+    generator_type: vits_generator
+    generator_params:
+        hidden_channels: 256
+        spks: -1
+        spk_embed_dim: 192
+        global_channels: 256
+        segment_size: 32
+        text_encoder_attention_heads: 4
+        text_encoder_ffn_expand: 4
+        text_encoder_blocks: 8
+        text_encoder_positionwise_layer_type: conv1d
+        text_encoder_positionwise_conv_kernel_size: 3
+        text_encoder_positional_encoding_layer_type: rel_pos
+        text_encoder_self_attention_layer_type: rel_selfattn
+        text_encoder_activation_type: swish
+        text_encoder_normalize_before: true
+        text_encoder_dropout_rate: 0.1
+        text_encoder_positional_dropout_rate: 0.0
+        text_encoder_attention_dropout_rate: 0.1
+        use_macaron_style_in_text_encoder: true
+        use_conformer_conv_in_text_encoder: false
+        text_encoder_conformer_kernel_size: -1
+        decoder_kernel_size: 7
+        decoder_channels: 768
+        decoder_upsample_scales:
+        - 8
+        - 8
+        - 2
+        - 2
+        decoder_upsample_kernel_sizes:
+        - 16
+        - 16
+        - 4
+        - 4
+        decoder_resblock_kernel_sizes:
+        - 3
+        - 7
+        - 11
+        decoder_resblock_dilations:
+        -   - 1
+            - 3
+            - 5
+        -   - 1
+            - 3
+            - 5
+        -   - 1
+            - 3
+            - 5
+        use_weight_norm_in_decoder: true
+        posterior_encoder_kernel_size: 5
+        posterior_encoder_layers: 16
+        posterior_encoder_stacks: 1
+        posterior_encoder_base_dilation: 1
+        posterior_encoder_dropout_rate: 0.0
+        use_weight_norm_in_posterior_encoder: true
+        flow_flows: 4
+        flow_kernel_size: 5
+        flow_base_dilation: 1
+        flow_layers: 4
+        flow_dropout_rate: 0.0
+        use_weight_norm_in_flow: true
+        use_only_mean_in_flow: true
+        stochastic_duration_predictor_kernel_size: 3
+        stochastic_duration_predictor_dropout_rate: 0.5
+        stochastic_duration_predictor_flows: 4
+        stochastic_duration_predictor_dds_conv_layers: 3
+        vocabs: 87
+        aux_channels: 513
+    discriminator_type: hifigan_multi_scale_multi_period_discriminator
+    discriminator_params:
+        scales: 1
+        scale_downsample_pooling: AvgPool1d
+        scale_downsample_pooling_params:
+            kernel_size: 4
+            stride: 2
+            padding: 2
+        scale_discriminator_params:
+            in_channels: 1
+            out_channels: 1
+            kernel_sizes:
+            - 15
+            - 41
+            - 5
+            - 3
+            channels: 128
+            max_downsample_channels: 1024
+            max_groups: 16
+            bias: true
+            downsample_scales:
+            - 2
+            - 2
+            - 4
+            - 4
+            - 1
+            nonlinear_activation: LeakyReLU
+            nonlinear_activation_params:
+                negative_slope: 0.1
+            use_weight_norm: true
+            use_spectral_norm: false
+        follow_official_norm: false
+        periods:
+        - 2
+        - 3
+        - 5
+        - 7
+        - 11
+        period_discriminator_params:
+            in_channels: 1
+            out_channels: 1
+            kernel_sizes:
+            - 5
+            - 3
+            channels: 32
+            downsample_scales:
+            - 3
+            - 3
+            - 3
+            - 3
+            - 1
+            max_downsample_channels: 1024
+            bias: true
+            nonlinear_activation: LeakyReLU
+            nonlinear_activation_params:
+                negative_slope: 0.1
+            use_weight_norm: true
+            use_spectral_norm: false
+    generator_adv_loss_params:
+        average_by_discriminators: false
+        loss_type: mse
+    discriminator_adv_loss_params:
+        average_by_discriminators: false
+        loss_type: mse
+    feat_match_loss_params:
+        average_by_discriminators: false
+        average_by_layers: false
+        include_final_outputs: true
+    mel_loss_params:
+        fs: 22050
+        n_fft: 1024
+        hop_length: 256
+        win_length: null
+        window: hann
+        n_mels: 80
+        fmin: 0
+        fmax: null
+        log_base: null
+    lambda_adv: 1.0
+    lambda_mel: 45.0
+    lambda_feat_match: 2.0
+    lambda_dur: 1.0
+    lambda_kl: 1.0
+    sampling_rate: 22050
+    cache_generator_outputs: true
+    plot_pred_mos: false
+    mos_pred_tool: utmos
+pitch_extract: null
+pitch_extract_conf: {}
+pitch_normalize: null
+pitch_normalize_conf: {}
+energy_extract: null
+energy_extract_conf: {}
+energy_normalize: null
+energy_normalize_conf: {}
+required:
+- output_dir
+- token_list
+version: '202509'
+distributed: true

meta.yaml

@@ -0,0 +1,8 @@
+espnet: '202511'
+files:
+  model_file: exp/tts_train_xvector_vits_large_grad_clip_original_batch_size_raw_phn_tacotron_g2p_en/785epoch.pth
+python: 3.11.14 (main, Oct 21 2025, 18:31:21) [GCC 11.2.0]
+timestamp: 1774480619.969943
+torch: 2.7.1+cu126
+yaml_files:
+  train_config: exp/tts_train_xvector_vits_large_grad_clip_original_batch_size_raw_phn_tacotron_g2p_en/config.yaml